Attention-throughout: a latent diffusion approach for single domain generalization in machinery fault diagnosis

作者
Yifan Wu,Chuan Li,Rui Liu,Dandan Zhao,Min Xia
出处
期刊:Advanced Engineering Informatics [Elsevier BV]
卷期号:74: 104706-104706
标识
DOI:10.1016/j.aei.2026.104706
摘要

Domain Generalization (DG) has been explored to achieve machine fault diagnosis under previously unseen operating conditions. However, most DG methods assume access to training data collected across multiple conditions, an assumption that rarely holds in industrial practice, where fault data are typically available from only a single operating condition. To address this critical constraint, we propose an attention-throughout latent diffusion model for single-source domain generalization (ATLD-SSDG). The proposed framework learns discriminative fault representations from a single-condition source domain and generalizes robustly to multiple unseen target conditions. First, to effectively capture complementary fault information, vibration signals from three views are fused and projected into a latent space via a collaborative attention fusion mechanism. Next, a dedicated one-dimensional (1D) U-Net is constructed to address information loss in existing approaches and facilitate more effective conditional diffusion. Unlike existing methods that directly adopt computer vision diffusion architectures, the proposed 1D U-Net is specifically designed for vibration signals, preserving localized fault-related details and preventing information loss caused by time–frequency transformations. Moreover, by explicitly regulating self-attention and cross-attention within the diffusion model, the framework preserves fault-relevant characteristics while selectively substituting operating-condition-related factors, thereby enabling controllable and effective domain generalization. Extensive experiments demonstrate superior generalization performance and diagnostic accuracy of the proposed method over state-of-the-art DG methods. These results indicate that latent diffusion, when properly structured for 1D condition-monitoring signals, provides an effective mechanism for single-source domain generalization, helping to close an important gap in DG research for predictive maintenance.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
汉堡包的应助被辰辰采纳,获得10
刚刚
七听的应助被聪慧栾采纳,获得30
刚刚
难过行恶发布了新的文献求助10
刚刚
elidan完成签到,获得积分10
刚刚
August完成签到,获得积分10
1秒前
香蕉觅云的应助被hua采纳,获得10
1秒前
1秒前
1秒前
老实的硬币完成签到,获得积分10
2秒前
2秒前
2秒前
科研通AI6.2的应助被kuku采纳,获得10
3秒前
mwzz233完成签到,获得积分10
3秒前
呆呆完成签到,获得积分10
3秒前
漂亮焦完成签到,获得积分10
3秒前
3秒前
呆呆完成签到,获得积分10
3秒前
姜雨杭发布了新的文献求助10
4秒前
4秒前
4秒前
4秒前
hhhhhjn发布了新的文献求助10
4秒前
且行发布了新的文献求助10
4秒前
睡衣完成签到,获得积分10
5秒前
fufu完成签到,获得积分10
6秒前
CipherSage的应助被蘑菇采纳,获得10
6秒前
凌慕发布了新的文献求助10
6秒前
zheng完成签到,获得积分10
6秒前
风吹麦浪的应助被dd采纳,获得10
6秒前
oasis完成签到,获得积分10
6秒前
巴啦啦完成签到,获得积分10
6秒前
7秒前
xiaoyang发布了新的文献求助10
7秒前
7秒前
7秒前
chillax7完成签到,获得积分10
7秒前
荼蘼发布了新的文献求助10
7秒前
张座铭完成签到,获得积分10
7秒前
斯文败类的应助被大傻逼采纳,获得10
7秒前
yxlsxz完成签到,获得积分10
7秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Social Psychology in the Real World 600
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8180807
求助须知:如何正确求助?哪些是违规求助? 9570895
关于积分的说明 21815089
捐赠科研通 7777155
什么是DOI,文献DOI怎么找? 3433347
关于科研通互助平台的介绍 2557613
邀请新用户注册赠送积分活动 2479317